Newest papers

HiMark: Hierarchical and Controllable Multi-bit Watermarking for Large Language Models

Ke Zhu, Yanli Chen, Ling Xiong, Gejian Zhao, Hanzhou Wu · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30601 · open-access PDF

Spanish

Con la rápida adopción de grandes modelos de lenguaje (LLM) en las aplicaciones de generación de texto, se ha vuelto cada vez más difícil rastrear el contenido generado y asignar la responsabilidad por su uso, lo que plantea preocupaciones sobre la procedencia, la protección de derechos de autor y la responsabilidad. El marcado por agua multi-bits aborda estos problemas mediante la incorporación de información de procedencia multi-bits en el texto generado, pero la extracción fiable sigue siendo difícil debido a la escasez de pruebas por bits y el equilibrio entre la exactitud de la extracción de watermark y la calidad del texto.

Machine translation (Meta M2M100); the English original follows.

Abstract

With the rapid adoption of large language models (LLMs) in text generation applications, it has become increasingly difficult to trace generated content and assign responsibility for its use, raising concerns about provenance, copyright protection, and accountability. Multi-bit watermarking addresses these issues by embedding multi-bit provenance information into generated text, but reliable extraction remains difficult due to sparse per-bit evidence and the trade-off between watermark-extraction accuracy and text quality. To deal with these challenges, we propose HiMark, a hierarchical and co

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30601, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange